文献速递心血管外周血管CT

CT血管造影中人工复核神经网络与手动方法测量主动脉直径的比较

Comparison of Human-in-the-Loop Neural Network and Manual Methods for Aortic Diameter Measurement at CT Angiography.
PubMed 文献 · Radiol Cardiothorac Imaging · 2025-01-01

本回顾性分析纳入177例胸主动脉扩张患者,比较U-Net自动测量联合人工复核(HITL)与技师手动测量胸主动脉直径的表现。HITL验证使95%一致性界限从-4.2~4.3 mm缩小至-2.9~3.4 mm,大偏差减少61%(从61次降至23次,P<.01);U-Net测量与血管变形映射衍生增长的ICC为0.74,高于手动测量的0.40(P<.01),结论认为HITL验证后的自动测量与参考标准一致性更强。

要点

  • U-Net自动测量经HITL验证后,95%一致性界限从-4.2~4.3 mm缩小至-2.9~3.4 mm。
  • HITL验证使大偏差(>5 mm)减少61%(从61次降至23次,P<.01)。
  • U-Net测量与血管变形映射衍生增长的ICC为0.74,高于手动测量的0.40(P<.01)。

核心结论

  • 经HITL验证的U-Net自动测量胸主动脉直径与参考标准评估的一致性优于手动临床测量。

研究设计与样本

  • 回顾性分析纳入2006年1月至2023年4月间至少两次CT血管造影的胸主动脉扩张患者177例(101例[57%]男性,中位年龄64岁[IQR 57-71]);手动直径由接受三维方法培训的技术员测量, multitask U-Net执行主动脉分割、标志点定位和自动直径测量后行HITL验证,直径差异大于5 mm者由专家重测;以直径无关的三维方法(血管变形映射)作为增长参考,采用Bland-Altman分析和组内相关系数评估一致性。

诊断标准与关键数值

  • 2028对配对测量中1955对(96%)通过HITL验证;HITL验证使95%一致性界限从-4.2~4.3 mm缩小至-2.9~3.4 mm,大偏差减少61%(从61次降至23次,P<.01);专家重测偏差与U-Net测量的平均差±SD为2.2 mm±1.7,低于与手动测量的7.0 mm±2.9(P<.01);U-Net测量较手动测量更易得到负增长值(OR 0.56,95%CI 0.44~0.70,P<.01);与血管变形映射衍生增长相比,U-Net测量的ICC为0.74(95%CI 0.62~0.80),手动测量为0.40(95%CI 0.18~0.56)(P<.01)。

临床应用与阅片要点

  • 作者结论认为,HITL验证后的U-Net自动测量胸主动脉直径与参考标准评估的一致性优于手动临床测量。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Purpose To compare the performance of a convolutional neural network (U-Net) with human-in-the-loop (HITL) validation against manual clinical measurements of thoracic aortic diameter at CT angiography. Materials and Methods This retrospective analysis included patients with thoracic aortic dilatation and at least two CT angiographic examinations between January 2006 and April 2023. Manual diameters were measured by technicians trained in the three-dimensional method. A multitask U-Net performed aortic segmentation, landmark localization, and automated aortic diameter measurements, followed by HITL validation. Discrepancies in diameter greater than 5 mm underwent expert remeasurement. Mid ascending aortic growth from U-Net and manual measurements were compared against a diameter-independent three-dimensional method (vascular deformation mapping). Agreement was assessed using Bland-Altman analysis and intraclass correlation coefficients. Results This study included 177 patients (101 [57%] male patients; median age, 64 years [IQR, 57-71]). Among 2028 paired measurements, 1955 (96%) passed the HITL validation. Validation reduced the 95% limits of agreement from -4.2 to 4.3 mm to -2.9 to 3.4 mm and reduced large discrepancies by 61% (from 61 to 23 measurements; P < .01). Expert remeasurements of discrepancies showed lower mean difference ± SD compared with U-Net measurements (2.2 mm ± 1.7 vs 7.0 mm ± 2.9; P < .01). U-Net measurements were more likely to yield negative growth values than manual measurements (odds ratio, 0.56; 95% CI: 0.44, 0.70; P < .01). Compared with vascular deformation mapping-derived growth, U-Net measurement showed stronger agreement than manual measurement (intraclass correlation coefficient, 0.74 [95% CI: 0.62, 0.80] vs 0.40 [95% CI: 0.18, 0.56]; P < .01). Conclusion Automated U-Net measurements of thoracic aorta diameters, when validated with an HITL approach, demonstrated stronger agreement with reference standard assessment than manual clinical measurements. Keywords: Aorta, Neural Networks, Vascular, CT Angiography, Segmentation, Thoracic Aortic Diameter Supplemental material is available for this article. © RSNA, 2025.

来源:Radiol Cardiothorac Imaging,查看原文。版权归原作者所有。

引用

  1. Marway PS, Campello Jorge CA, Baker T, et al. Comparison of Human-in-the-Loop Neural Network and Manual Methods for Aortic Diameter Measurement at CT Angiography. Radiol Cardiothorac Imaging. 2025. PMID: 41196190. doi:10.1148/ryct.240490

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。